INDEX
Explanations
references to the term "Bull" in contexts unrelated to the animal
references to the word "Bull."
New Auto-Interp
Negative Logits
ALLY
-0.84
ALS
-0.80
MENTS
-0.80
MENT
-0.76
Genie
-0.74
SPONSORED
-0.69
ãģ¦
-0.67
éĥ
-0.66
Centauri
-0.65
TERN
-0.64
POSITIVE LOGITS
shit
1.07
dog
1.00
ocks
0.97
fights
0.96
ock
0.95
iard
0.94
fighter
0.93
ying
0.90
keye
0.90
ies
0.90
Activations Density 0.039%